Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that create connections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     but
    -0.17
     though
    -0.17
    ÙĤØ©
    -0.16
     and
    -0.16
    ucci
    -0.15
    ci
    -0.14
    vik
    -0.14
    бÑĥÑĢг
    -0.14
    UI
    -0.14
    _PIXEL
    -0.14
    POSITIVE LOGITS
    VERRIDE
    0.16
    ëĶĶìĸ´
    0.16
    ADDING
    0.15
    .Companion
    0.15
     ÙĦÙĥ
    0.15
    phins
    0.14
     [],č↵
    0.14
    ÅĤÄħ
    0.14
    azar
    0.14
    umber
    0.14
    Act Density 0.290%

    No Known Activations